line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
# WordNet::Tools v2.05 |
2
|
|
|
|
|
|
|
# (Last updated $Id: Tools.pm,v 1.5 2008/06/04 18:38:01 sidz1979 Exp $) |
3
|
|
|
|
|
|
|
# |
4
|
|
|
|
|
|
|
# This module provides some WordNet tools for use with the |
5
|
|
|
|
|
|
|
# WordNet::Similarity modules. |
6
|
|
|
|
|
|
|
# |
7
|
|
|
|
|
|
|
# Copyright (c) 2005, |
8
|
|
|
|
|
|
|
# |
9
|
|
|
|
|
|
|
# Ted Pedersen, University of Minnesota Duluth |
10
|
|
|
|
|
|
|
# tpederse at d.umn.edu |
11
|
|
|
|
|
|
|
# |
12
|
|
|
|
|
|
|
# Siddharth Patwardhan, University of Utah, Salt Lake City |
13
|
|
|
|
|
|
|
# sidd at cs.utah.edu |
14
|
|
|
|
|
|
|
# |
15
|
|
|
|
|
|
|
# This program is free software; you can redistribute it and/or |
16
|
|
|
|
|
|
|
# modify it under the terms of the GNU General Public License |
17
|
|
|
|
|
|
|
# as published by the Free Software Foundation; either version 2 |
18
|
|
|
|
|
|
|
# of the License, or (at your option) any later version. |
19
|
|
|
|
|
|
|
# |
20
|
|
|
|
|
|
|
# This program is distributed in the hope that it will be useful, |
21
|
|
|
|
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
22
|
|
|
|
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
23
|
|
|
|
|
|
|
# GNU General Public License for more details. |
24
|
|
|
|
|
|
|
# |
25
|
|
|
|
|
|
|
# You should have received a copy of the GNU General Public License |
26
|
|
|
|
|
|
|
# along with this program; if not, write to |
27
|
|
|
|
|
|
|
# |
28
|
|
|
|
|
|
|
# The Free Software Foundation, Inc., |
29
|
|
|
|
|
|
|
# 59 Temple Place - Suite 330, |
30
|
|
|
|
|
|
|
# Boston, MA 02111-1307, USA. |
31
|
|
|
|
|
|
|
# |
32
|
|
|
|
|
|
|
# ------------------------------------------------------------------ |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
package WordNet::Tools; |
35
|
|
|
|
|
|
|
|
36
|
|
|
|
|
|
|
=head1 NAME |
37
|
|
|
|
|
|
|
|
38
|
|
|
|
|
|
|
WordNet::Tools - Some tools for use with WordNet. |
39
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
=head1 SYNOPSIS |
41
|
|
|
|
|
|
|
|
42
|
|
|
|
|
|
|
use WordNet::QueryData; |
43
|
|
|
|
|
|
|
|
44
|
|
|
|
|
|
|
use WordNet::Tools; |
45
|
|
|
|
|
|
|
|
46
|
|
|
|
|
|
|
my $wn = WordNet::QueryData->new; |
47
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
my $wntools = WordNet::Tools->new($wn); |
49
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
my $wnHashCode = $wntools->hashCode(); |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
my $newstring = $wntools->compoundify("find compound words like new york city in this text"); |
53
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
=head1 DESCRIPTION |
55
|
|
|
|
|
|
|
|
56
|
|
|
|
|
|
|
This module provides some tools for use with WordNet. For example, the |
57
|
|
|
|
|
|
|
'compoundify' method detects compound words (as found in WordNet) in a |
58
|
|
|
|
|
|
|
text string and it combines these words into single tokens using |
59
|
|
|
|
|
|
|
underscore separators. Another tool in this module generates a unique |
60
|
|
|
|
|
|
|
hash code corresponding to a WordNet distribution. This hash code is |
61
|
|
|
|
|
|
|
meant to replace the "version" information in WordNet, which is no |
62
|
|
|
|
|
|
|
longer reliable. |
63
|
|
|
|
|
|
|
|
64
|
|
|
|
|
|
|
=head1 METHODS |
65
|
|
|
|
|
|
|
|
66
|
|
|
|
|
|
|
The following methods are defined: |
67
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
=over |
69
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
=cut |
71
|
|
|
|
|
|
|
|
72
|
19
|
|
|
19
|
|
133227
|
use strict; |
|
19
|
|
|
|
|
34
|
|
|
19
|
|
|
|
|
614
|
|
73
|
19
|
|
|
19
|
|
96
|
use warnings; |
|
19
|
|
|
|
|
33
|
|
|
19
|
|
|
|
|
560
|
|
74
|
19
|
|
|
19
|
|
101
|
use Exporter; |
|
19
|
|
|
|
|
39
|
|
|
19
|
|
|
|
|
912
|
|
75
|
19
|
|
|
19
|
|
33286
|
use WordNet::QueryData; |
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
use Digest::SHA1 qw(sha1_base64); |
77
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
use constant MAX_COMPOUND_SIZE => 9; |
79
|
|
|
|
|
|
|
|
80
|
|
|
|
|
|
|
our @ISA = qw(Exporter); |
81
|
|
|
|
|
|
|
our $VERSION = '2.05'; |
82
|
|
|
|
|
|
|
|
83
|
|
|
|
|
|
|
=item WordNet::Tools->new($wn) |
84
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
This is a constructor for this class (and creates a new object of this |
86
|
|
|
|
|
|
|
class). It requires a WordNet::QueryData object as a parameter. |
87
|
|
|
|
|
|
|
|
88
|
|
|
|
|
|
|
Parameters: $wn -- a WordNet::QueryData object. |
89
|
|
|
|
|
|
|
|
90
|
|
|
|
|
|
|
Returns: a new WordNet::Tools object. |
91
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
=cut |
93
|
|
|
|
|
|
|
|
94
|
|
|
|
|
|
|
# Constructor for this module |
95
|
|
|
|
|
|
|
sub new |
96
|
|
|
|
|
|
|
{ |
97
|
|
|
|
|
|
|
my $class = shift; |
98
|
|
|
|
|
|
|
my $wn = shift; |
99
|
|
|
|
|
|
|
my $self = {}; |
100
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
# Create the preprocessor object |
102
|
|
|
|
|
|
|
$class = ref $class || $class; |
103
|
|
|
|
|
|
|
bless($self, $class); |
104
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
# Verify the given WordNet::QueryData object |
106
|
|
|
|
|
|
|
return undef if(!defined $wn || !ref $wn || ref($wn) ne "WordNet::QueryData"); |
107
|
|
|
|
|
|
|
$self->{wn} = $wn; |
108
|
|
|
|
|
|
|
|
109
|
|
|
|
|
|
|
# Get the compounds from WordNet |
110
|
|
|
|
|
|
|
foreach my $pos ('n', 'v', 'a', 'r') |
111
|
|
|
|
|
|
|
{ |
112
|
|
|
|
|
|
|
foreach my $word ($wn->listAllWords($pos)) |
113
|
|
|
|
|
|
|
{ |
114
|
|
|
|
|
|
|
$self->{compounds}->{$word} = 1 if ($word =~ /_/); |
115
|
|
|
|
|
|
|
} |
116
|
|
|
|
|
|
|
} |
117
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
# Compute the WordNet hash-code and store |
119
|
|
|
|
|
|
|
$self->{hashcode} = $self->_computeHashCode(); |
120
|
|
|
|
|
|
|
return undef if(!defined($self->{hashcode})); |
121
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
return $self; |
123
|
|
|
|
|
|
|
} |
124
|
|
|
|
|
|
|
|
125
|
|
|
|
|
|
|
=item $wntools->compoundify($string) |
126
|
|
|
|
|
|
|
|
127
|
|
|
|
|
|
|
This is method identifies all compound words occurring in the given input |
128
|
|
|
|
|
|
|
string. Compound words are multi-word tokens appearing in WordNet. |
129
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
Parameters: $string -- an input text string. |
131
|
|
|
|
|
|
|
|
132
|
|
|
|
|
|
|
Returns: a string with compound words identified. |
133
|
|
|
|
|
|
|
|
134
|
|
|
|
|
|
|
=cut |
135
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
# Detect compounds in a block of text |
137
|
|
|
|
|
|
|
sub compoundify |
138
|
|
|
|
|
|
|
{ |
139
|
|
|
|
|
|
|
my $self = shift; |
140
|
|
|
|
|
|
|
my $block = shift; |
141
|
|
|
|
|
|
|
|
142
|
|
|
|
|
|
|
return $block if(!defined $block || !ref $self || !defined $self->{compounds}); |
143
|
|
|
|
|
|
|
|
144
|
|
|
|
|
|
|
my $string; |
145
|
|
|
|
|
|
|
my $done; |
146
|
|
|
|
|
|
|
my $temp; |
147
|
|
|
|
|
|
|
my $firstPointer; |
148
|
|
|
|
|
|
|
my $secondPointer; |
149
|
|
|
|
|
|
|
my @wordsArray; |
150
|
|
|
|
|
|
|
|
151
|
|
|
|
|
|
|
# get all the words into an array |
152
|
|
|
|
|
|
|
@wordsArray = (); |
153
|
|
|
|
|
|
|
while($block =~ /([a-zA-Z0-9_\.\-\/\']+)/g) |
154
|
|
|
|
|
|
|
{ |
155
|
|
|
|
|
|
|
push(@wordsArray, $1); |
156
|
|
|
|
|
|
|
} |
157
|
|
|
|
|
|
|
|
158
|
|
|
|
|
|
|
# now compoundify, GREEDILY!! |
159
|
|
|
|
|
|
|
$firstPointer = 0; |
160
|
|
|
|
|
|
|
$string = ""; |
161
|
|
|
|
|
|
|
|
162
|
|
|
|
|
|
|
while($firstPointer <= $#wordsArray) |
163
|
|
|
|
|
|
|
{ |
164
|
|
|
|
|
|
|
$secondPointer = (($#wordsArray > ($firstPointer + MAX_COMPOUND_SIZE - 1)) ? ($firstPointer + MAX_COMPOUND_SIZE - 1) : ($#wordsArray)); |
165
|
|
|
|
|
|
|
$done = 0; |
166
|
|
|
|
|
|
|
while(($secondPointer > $firstPointer) && !$done) |
167
|
|
|
|
|
|
|
{ |
168
|
|
|
|
|
|
|
$temp = join("_", @wordsArray[$firstPointer .. $secondPointer]); |
169
|
|
|
|
|
|
|
if(defined $self->{compounds}->{$temp}) |
170
|
|
|
|
|
|
|
{ |
171
|
|
|
|
|
|
|
$string .= "$temp "; |
172
|
|
|
|
|
|
|
$done = 1; |
173
|
|
|
|
|
|
|
} |
174
|
|
|
|
|
|
|
else |
175
|
|
|
|
|
|
|
{ |
176
|
|
|
|
|
|
|
$secondPointer--; |
177
|
|
|
|
|
|
|
} |
178
|
|
|
|
|
|
|
} |
179
|
|
|
|
|
|
|
$string .= "$wordsArray[$firstPointer] " unless($done); |
180
|
|
|
|
|
|
|
$firstPointer = $secondPointer + 1; |
181
|
|
|
|
|
|
|
} |
182
|
|
|
|
|
|
|
$string =~ s/\s+$//; |
183
|
|
|
|
|
|
|
|
184
|
|
|
|
|
|
|
return $string; |
185
|
|
|
|
|
|
|
} |
186
|
|
|
|
|
|
|
|
187
|
|
|
|
|
|
|
=item $wntools->getCompoundsList() |
188
|
|
|
|
|
|
|
|
189
|
|
|
|
|
|
|
This method returns the list of compound words present in WordNet. |
190
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
Parameters: none |
192
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
Returns: reference to an array of compounds. |
194
|
|
|
|
|
|
|
|
195
|
|
|
|
|
|
|
=cut |
196
|
|
|
|
|
|
|
|
197
|
|
|
|
|
|
|
# Return the list of WordNet compounds |
198
|
|
|
|
|
|
|
# Since a deep-copy is performed, this method can be slow. Consequently, |
199
|
|
|
|
|
|
|
# this method should be used sparingly |
200
|
|
|
|
|
|
|
sub getCompoundsList |
201
|
|
|
|
|
|
|
{ |
202
|
|
|
|
|
|
|
my $self = shift; |
203
|
|
|
|
|
|
|
my @cList = keys(%{$self->{compounds}}); |
204
|
|
|
|
|
|
|
return \@cList; |
205
|
|
|
|
|
|
|
} |
206
|
|
|
|
|
|
|
|
207
|
|
|
|
|
|
|
=item $wntools->hashCode() |
208
|
|
|
|
|
|
|
|
209
|
|
|
|
|
|
|
This is method returns a unique identifier representing a specific |
210
|
|
|
|
|
|
|
distribution of WordNet. |
211
|
|
|
|
|
|
|
|
212
|
|
|
|
|
|
|
Parameters: none. |
213
|
|
|
|
|
|
|
|
214
|
|
|
|
|
|
|
Returns: a unique identifier (string). |
215
|
|
|
|
|
|
|
|
216
|
|
|
|
|
|
|
=cut |
217
|
|
|
|
|
|
|
|
218
|
|
|
|
|
|
|
# Return the computed hash-code |
219
|
|
|
|
|
|
|
sub hashCode |
220
|
|
|
|
|
|
|
{ |
221
|
|
|
|
|
|
|
my $self = shift; |
222
|
|
|
|
|
|
|
return $self->{hashcode}; |
223
|
|
|
|
|
|
|
} |
224
|
|
|
|
|
|
|
|
225
|
|
|
|
|
|
|
# Compute the hash code for the given WordNet distribution |
226
|
|
|
|
|
|
|
# Most of this code was written by Ben Haskell |
227
|
|
|
|
|
|
|
sub _computeHashCode |
228
|
|
|
|
|
|
|
{ |
229
|
|
|
|
|
|
|
my $self = shift; |
230
|
|
|
|
|
|
|
my $qd = $self->{wn}; |
231
|
|
|
|
|
|
|
return undef if(!defined($qd)); |
232
|
|
|
|
|
|
|
|
233
|
|
|
|
|
|
|
my $dir = $qd->dataPath(); |
234
|
|
|
|
|
|
|
my $pos = '{noun,verb,adj,adv}'; |
235
|
|
|
|
|
|
|
my @files = sort grep -f, map glob("\Q$dir\E/$_"), "{index,data}.$pos", "$pos.{idx,dat}"; |
236
|
|
|
|
|
|
|
|
237
|
|
|
|
|
|
|
# (stat)[7] returns file size in bytes |
238
|
|
|
|
|
|
|
my $concat = join '.', map { (stat)[7] } @files; |
239
|
|
|
|
|
|
|
return sha1_base64($concat); |
240
|
|
|
|
|
|
|
} |
241
|
|
|
|
|
|
|
|
242
|
|
|
|
|
|
|
1; |
243
|
|
|
|
|
|
|
|
244
|
|
|
|
|
|
|
__END__ |